• ETRI Journal
• /
• v.30 no.1
• /
• pp.155-157
• /
• 2008

This letter introduces a new method to automatically acquire paraphrases using bilingual corpora. It utilizes the bilingual dependency relations obtained by projecting a monolingual dependency parse onto the other language's sentence based on statistical alignment techniques. Since the proposed paraphrasing method can clearly disambiguate the sense of the original phrases using the bilingual context of dependency relations, it would be possible to obtain interchangeable paraphrases under a given context. Through experiments with parallel corpora of Korean and English language pairs, we demonstrate that our method effectively extracts paraphrases with high precision, achieving success rates of 94.3% and 84.6%, respectively, for Korean and English.

• Proceedings of the Korea Society of Design Studies Conference
• /
• 2004.10a
• /
• pp.94-95
• /
• 2004

• ETRI Journal
• /
• v.28 no.6
• /
• pp.803-806
• /
• 2006

This letter addresses a structural disambiguation method for Korean adverbs based on the correlative relation constraints between adverbs and modifiees, and the morphological context information of sentences. Using the proposed method, we improved the dependency parsing accuracy of adverbs from 79.2 to 89%. The experimental result shows that the proposed method is especially expert in parsing adverbs which can modify multiple word classes or have a long distance dependency relation to their modifiees.

• Journal of The Korean Association For Science Education
• /
• v.26 no.3
• /
• pp.406-414
• /
• 2006

This study investigated 7th grade students' context dependency on explanations about propagating path of light in three different contextual problems: observation of an object, observation of an object's image in a mirror, and observation of one's own face reflection in a mirror. Researchers examined student response in each context through interviews. The students were classified into four groups according to their explanations for the three different contexts. Each group was redivided into two or three subgroups in accordance with their conceptual features. After that, researchers investigated the characteristics of each subgroup. Main findings of the study indicated that (1) group 1 students' conceptions differed in each context; (2) group 2 students showed scientific conceptions in C1 context but in C2 context they showed visual ray conceptions or image misconceptions; (3) group 3 students did not show scientific conceptions in C3 context by strong misconceptions about one's own face reflection in the mirror. Also, this paper discussed the educational implications of the results.

• KIISE Transactions on Computing Practices
• /
• v.21 no.8
• /
• pp.567-571
• /
• 2015

Transition-based dependency parsing requires much time and efforts to design and select features from a very large number of possible combinations. Recent studies have successfully applied Multi-Layer Perceptrons (MLP) to find solutions to this problem and to reduce the data sparseness. However, most of these methods have adopted greedy search and can only consider a limited amount of information from the context window. In this study, we use a Recurrent Neural Network to handle long dependencies between sub dependency trees of current state and current transition action. The results indicate that our method provided a higher accuracy (UAS) than an MLP based model.

• MALSORI
• /
• v.68
• /
• pp.33-47
• /
• 2008

In this paper, we propose a hybrid acoustic and pronunciation model adaptation method based on context dependency for Korean-English speech recognition. The proposed method is performed as follows. First, in order to derive pronunciation variant rules, an n-best phoneme sequence is obtained by phone recognition. Second, we decompose each rule into a context independent (CI) or a context dependent (CD) one. To this end, it is assumed that a different phoneme structure between Korean and English makes CI pronunciation variabilities while coarticulation effects are related to CD pronunciation variabilities. Finally, we perform an acoustic model adaptation and a pronunciation model adaptation for CI and CD pronunciation variabilities, respectively. It is shown from the Korean-English speech recognition experiments that the average word error rate (WER) is decreased by 36.0% when compared to the baseline that does not include any adaptation. In addition, the proposed method has a lower average WER than either the acoustic model adaptation or the pronunciation model adaptation.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.379-387
• /
• 2003

A lot of microbial genome projects have been completed to pour the enormous amount of genomic sequence data. In this context. the problem of identifying promoters in genomic DNA sequences by computational methods has attracted considerable research attention in recent years. In this paper, we propose a new model of prokaryotic core promoter region including the -10 region and transcription initiation site, that is Dependency-Reflecting Decomposition Model (DRDM), which captures the most significant biological dependencies between positions (allowing for non-adjacent as well as adjacent dependencies). DRDM showed a good result of performance test and it will be employed effectively in predicting promoters in long microbial genomic Contigs.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 1998.02a
• /
• pp.195-205
• /
• 1998

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.8
• /
• pp.394-406
• /
• 2008

Even though context is the most important feature in context-aware systems, the existing requirements engineering cannot support methodology for elicitation and specification of contexts. In this paper, we propose a requirements elicitation method and a requirements specification method for context-aware systems. Our requirements elicitation method is a 6-stepped, incremental, and iterative process. At the beginning steps in the process, we identify the requirements for business logic. Afterwards, we gather the requirements for context logic, model contexts, and identify subsystems. For requirements specification, we suggest a context-aware use case diagram, a context diagram for context modeling, and a context-type-use-case-dependency diagram for the traceability of use cases on the change of context types. We also introduce a case study that we apply our approaches to a real system, and a qualitative evaluation of our approaches. Our study will help stakeholders to efficiently elicit requirements for context-aware systems and to specify them clearly.

• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1365-1375
• /
• 2016

One of the most important capabilities for autonomous service robots working in living environments is to recognize and understand the correct context in dynamically changing environment. To generate high-level context knowledge for decision-making from multiple sensory data streams, many technical problems such as multi-modal sensory data fusion, uncertainty handling, symbolic knowledge grounding, time dependency, dynamics, and time-constrained spatio-temporal reasoning should be solved. Considering these problems, this paper proposes an effective dynamic context management and spatio-temporal reasoning method for intelligent service robots. In order to guarantee efficient context management and reasoning, our algorithm was designed to generate low-level context knowledge reactively for every input sensory or perception data, while postponing high-level context knowledge generation until it was demanded by the decision-making module. When high-level context knowledge is demanded, it is derived through backward spatio-temporal reasoning. In experiments with Turtlebot using Kinect visual sensor, the dynamic context management and spatio-temporal reasoning system based on the proposed method showed high performance.